Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm fixes from Paolo Bonzini:

 - Allow again loading KVM on 32-bit non-PAE builds

 - Fixes for host SMIs on AMD

 - Fixes for guest SMIs on AMD

 - Fixes for selftests on s390 and ARM

 - Fix memory leak

 - Enforce no-instrumentation area on vmentry when hardware breakpoints
   are in use.

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (25 commits)
  KVM: selftests: smm_test: Test SMM enter from L2
  KVM: nSVM: Restore nested control upon leaving SMM
  KVM: nSVM: Fix L1 state corruption upon return from SMM
  KVM: nSVM: Introduce svm_copy_vmrun_state()
  KVM: nSVM: Check that VM_HSAVE_PA MSR was set before VMRUN
  KVM: nSVM: Check the value written to MSR_VM_HSAVE_PA
  KVM: SVM: Fix sev_pin_memory() error checks in SEV migration utilities
  KVM: SVM: Return -EFAULT if copy_to_user() for SEV mig packet header fails
  KVM: SVM: add module param to control the #SMI interception
  KVM: SVM: remove INIT intercept handler
  KVM: SVM: #SMI interception must not skip the instruction
  KVM: VMX: Remove vmx_msr_index from vmx.h
  KVM: X86: Disable hardware breakpoints unconditionally before kvm_x86->run()
  KVM: selftests: Address extra memslot parameters in vm_vaddr_alloc
  kvm: debugfs: fix memory leak in kvm_create_vm_debugfs
  KVM: x86/pmu: Clear anythread deprecated bit when 0xa leaf is unsupported on the SVM
  KVM: mmio: Fix use-after-free Read in kvm_vm_ioctl_unregister_coalesced_mmio
  KVM: SVM: Revert clearing of C-bit on GPA in #NPF handler
  KVM: x86/mmu: Do not apply HPA (memory encryption) mask to GPAs
  KVM: x86: Use kernel's x86_phys_bits to handle reduced MAXPHYADDR
  ...

21 files changed, 255 insertions, 64 deletions

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index c42613cfb5ba6d..739be5da3bca78 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -765,7 +765,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 
 		edx.split.num_counters_fixed = min(cap.num_counters_fixed, MAX_FIXED_COUNTERS);
 		edx.split.bit_width_fixed = cap.bit_width_fixed;
-		edx.split.anythread_deprecated = 1;
+		if (cap.version)
+			edx.split.anythread_deprecated = 1;
 		edx.split.reserved1 = 0;
 		edx.split.reserved2 = 0;
 
@@ -940,8 +941,21 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		unsigned virt_as = max((entry->eax >> 8) & 0xff, 48U);
 		unsigned phys_as = entry->eax & 0xff;
 
-		if (!g_phys_as)
+		/*
+		 * If TDP (NPT) is disabled use the adjusted host MAXPHYADDR as
+		 * the guest operates in the same PA space as the host, i.e.
+		 * reductions in MAXPHYADDR for memory encryption affect shadow
+		 * paging, too.
+		 *
+		 * If TDP is enabled but an explicit guest MAXPHYADDR is not
+		 * provided, use the raw bare metal MAXPHYADDR as reductions to
+		 * the HPAs do not affect GPAs.
+		 */
+		if (!tdp_enabled)
+			g_phys_as = boot_cpu_data.x86_phys_bits;
+		else if (!g_phys_as)
 			g_phys_as = phys_as;
+
 		entry->eax = g_phys_as | (virt_as << 8);
 		entry->edx = 0;
 		cpuid_entry_override(entry, CPUID_8000_0008_EBX);
@@ -964,12 +978,18 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 	case 0x8000001a:
 	case 0x8000001e:
 		break;
-	/* Support memory encryption cpuid if host supports it */
 	case 0x8000001F:
-		if (!kvm_cpu_cap_has(X86_FEATURE_SEV))
+		if (!kvm_cpu_cap_has(X86_FEATURE_SEV)) {
 			entry->eax = entry->ebx = entry->ecx = entry->edx = 0;
-		else
+		} else {
 			cpuid_entry_override(entry, CPUID_8000_001F_EAX);
+
+			/*
+			 * Enumerate '0' for "PA bits reduction", the adjusted
+			 * MAXPHYADDR is enumerated directly (see 0x80000008).
+			 */
+			entry->ebx &= ~GENMASK(11, 6);
+		}
 		break;
 	/*Add support for Centaur's CPUID instruction*/
 	case 0xC0000000:
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 845d114ae07547..66f7f5bc3482c5 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -53,6 +53,8 @@
 #include <asm/kvm_page_track.h>
 #include "trace.h"
 
+#include "paging.h"
+
 extern bool itlb_multihit_kvm_mitigation;
 
 int __read_mostly nx_huge_pages = -1;
diff --git a/arch/x86/kvm/mmu/paging.h b/arch/x86/kvm/mmu/paging.h
new file mode 100644
index 00000000000000..de8ab323bb7076
--- /dev/null
+++ b/arch/x86/kvm/mmu/paging.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Shadow paging constants/helpers that don't need to be #undef'd. */
+#ifndef __KVM_X86_PAGING_H
+#define __KVM_X86_PAGING_H
+
+#define GUEST_PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))
+#define PT64_LVL_ADDR_MASK(level) \
+	(GUEST_PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \
+						* PT64_LEVEL_BITS))) - 1))
+#define PT64_LVL_OFFSET_MASK(level) \
+	(GUEST_PT64_BASE_ADDR_MASK & ((1ULL << (PAGE_SHIFT + (((level) - 1) \
+						* PT64_LEVEL_BITS))) - 1))
+#endif /* __KVM_X86_PAGING_H */
+
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 490a028ddabe98..ee044d357b5f98 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -24,7 +24,7 @@
 	#define pt_element_t u64
 	#define guest_walker guest_walker64
 	#define FNAME(name) paging##64_##name
-	#define PT_BASE_ADDR_MASK PT64_BASE_ADDR_MASK
+	#define PT_BASE_ADDR_MASK GUEST_PT64_BASE_ADDR_MASK
 	#define PT_LVL_ADDR_MASK(lvl) PT64_LVL_ADDR_MASK(lvl)
 	#define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl)
 	#define PT_INDEX(addr, level) PT64_INDEX(addr, level)
@@ -57,7 +57,7 @@
 	#define pt_element_t u64
 	#define guest_walker guest_walkerEPT
 	#define FNAME(name) ept_##name
-	#define PT_BASE_ADDR_MASK PT64_BASE_ADDR_MASK
+	#define PT_BASE_ADDR_MASK GUEST_PT64_BASE_ADDR_MASK
 	#define PT_LVL_ADDR_MASK(lvl) PT64_LVL_ADDR_MASK(lvl)
 	#define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl)
 	#define PT_INDEX(addr, level) PT64_INDEX(addr, level)
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index 7a5ce931410755..eb7b227fc6cfe1 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -38,12 +38,6 @@ static_assert(SPTE_TDP_AD_ENABLED_MASK == 0);
 #else
 #define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))
 #endif
-#define PT64_LVL_ADDR_MASK(level) \
-	(PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \
-						* PT64_LEVEL_BITS))) - 1))
-#define PT64_LVL_OFFSET_MASK(level) \
-	(PT64_BASE_ADDR_MASK & ((1ULL << (PAGE_SHIFT + (((level) - 1) \
-						* PT64_LEVEL_BITS))) - 1))
 
 #define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | shadow_user_mask \
 			| shadow_x_mask | shadow_nx_mask | shadow_me_mask)
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 21d03e3a5dfd52..3bd09c50c98b63 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -154,6 +154,10 @@ void recalc_intercepts(struct vcpu_svm *svm)
 
 	for (i = 0; i < MAX_INTERCEPT; i++)
 		c->intercepts[i] |= g->intercepts[i];
+
+	/* If SMI is not intercepted, ignore guest SMI intercept as well  */
+	if (!intercept_smi)
+		vmcb_clr_intercept(c, INTERCEPT_SMI);
 }
 
 static void copy_vmcb_control_area(struct vmcb_control_area *dst,
@@ -304,8 +308,8 @@ static bool nested_vmcb_valid_sregs(struct kvm_vcpu *vcpu,
 	return true;
 }
 
-static void nested_load_control_from_vmcb12(struct vcpu_svm *svm,
-					    struct vmcb_control_area *control)
+void nested_load_control_from_vmcb12(struct vcpu_svm *svm,
+				     struct vmcb_control_area *control)
 {
 	copy_vmcb_control_area(&svm->nested.ctl, control);
 
@@ -618,6 +622,11 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu)
 	struct kvm_host_map map;
 	u64 vmcb12_gpa;
 
+	if (!svm->nested.hsave_msr) {
+		kvm_inject_gp(vcpu, 0);
+		return 1;
+	}
+
 	if (is_smm(vcpu)) {
 		kvm_queue_exception(vcpu, UD_VECTOR);
 		return 1;
@@ -692,6 +701,27 @@ out:
 	return ret;
 }
 
+/* Copy state save area fields which are handled by VMRUN */
+void svm_copy_vmrun_state(struct vmcb_save_area *from_save,
+			  struct vmcb_save_area *to_save)
+{
+	to_save->es = from_save->es;
+	to_save->cs = from_save->cs;
+	to_save->ss = from_save->ss;
+	to_save->ds = from_save->ds;
+	to_save->gdtr = from_save->gdtr;
+	to_save->idtr = from_save->idtr;
+	to_save->rflags = from_save->rflags | X86_EFLAGS_FIXED;
+	to_save->efer = from_save->efer;
+	to_save->cr0 = from_save->cr0;
+	to_save->cr3 = from_save->cr3;
+	to_save->cr4 = from_save->cr4;
+	to_save->rax = from_save->rax;
+	to_save->rsp = from_save->rsp;
+	to_save->rip = from_save->rip;
+	to_save->cpl = 0;
+}
+
 void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb)
 {
 	to_vmcb->save.fs = from_vmcb->save.fs;
@@ -1355,28 +1385,11 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
 
 	svm->nested.vmcb12_gpa = kvm_state->hdr.svm.vmcb_pa;
 
-	svm->vmcb01.ptr->save.es = save->es;
-	svm->vmcb01.ptr->save.cs = save->cs;
-	svm->vmcb01.ptr->save.ss = save->ss;
-	svm->vmcb01.ptr->save.ds = save->ds;
-	svm->vmcb01.ptr->save.gdtr = save->gdtr;
-	svm->vmcb01.ptr->save.idtr = save->idtr;
-	svm->vmcb01.ptr->save.rflags = save->rflags | X86_EFLAGS_FIXED;
-	svm->vmcb01.ptr->save.efer = save->efer;
-	svm->vmcb01.ptr->save.cr0 = save->cr0;
-	svm->vmcb01.ptr->save.cr3 = save->cr3;
-	svm->vmcb01.ptr->save.cr4 = save->cr4;
-	svm->vmcb01.ptr->save.rax = save->rax;
-	svm->vmcb01.ptr->save.rsp = save->rsp;
-	svm->vmcb01.ptr->save.rip = save->rip;
-	svm->vmcb01.ptr->save.cpl = 0;
-
+	svm_copy_vmrun_state(save, &svm->vmcb01.ptr->save);
 	nested_load_control_from_vmcb12(svm, ctl);
 
 	svm_switch_vmcb(svm, &svm->nested.vmcb02);
-
 	nested_vmcb02_prepare_control(svm);
-
 	kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
 	ret = 0;
 out_free:
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 62926f1a5f7ba4..6710d9ee2e4b2c 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -1272,8 +1272,8 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	/* Pin guest memory */
 	guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK,
 				    PAGE_SIZE, &n, 0);
-	if (!guest_page)
-		return -EFAULT;
+	if (IS_ERR(guest_page))
+		return PTR_ERR(guest_page);
 
 	/* allocate memory for header and transport buffer */
 	ret = -ENOMEM;
@@ -1310,8 +1310,9 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	}
 
 	/* Copy packet header to userspace. */
-	ret = copy_to_user((void __user *)(uintptr_t)params.hdr_uaddr, hdr,
-				params.hdr_len);
+	if (copy_to_user((void __user *)(uintptr_t)params.hdr_uaddr, hdr,
+			 params.hdr_len))
+		ret = -EFAULT;
 
 e_free_trans_data:
 	kfree(trans_data);
@@ -1463,11 +1464,12 @@ static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	data.trans_len = params.trans_len;
 
 	/* Pin guest memory */
-	ret = -EFAULT;
 	guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK,
 				    PAGE_SIZE, &n, 0);
-	if (!guest_page)
+	if (IS_ERR(guest_page)) {
+		ret = PTR_ERR(guest_page);
 		goto e_free_trans;
+	}
 
 	/* The RECEIVE_UPDATE_DATA command requires C-bit to be always set. */
 	data.guest_address = (page_to_pfn(guest_page[0]) << PAGE_SHIFT) + offset;
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 8834822c00cdcc..664d20f0689c8b 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -198,6 +198,11 @@ module_param(avic, bool, 0444);
 bool __read_mostly dump_invalid_vmcb;
 module_param(dump_invalid_vmcb, bool, 0644);
 
+
+bool intercept_smi = true;
+module_param(intercept_smi, bool, 0444);
+
+
 static bool svm_gp_erratum_intercept = true;
 
 static u8 rsm_ins_bytes[] = "\x0f\xaa";
@@ -1185,7 +1190,10 @@ static void init_vmcb(struct kvm_vcpu *vcpu)
 
 	svm_set_intercept(svm, INTERCEPT_INTR);
 	svm_set_intercept(svm, INTERCEPT_NMI);
-	svm_set_intercept(svm, INTERCEPT_SMI);
+
+	if (intercept_smi)
+		svm_set_intercept(svm, INTERCEPT_SMI);
+
 	svm_set_intercept(svm, INTERCEPT_SELECTIVE_CR0);
 	svm_set_intercept(svm, INTERCEPT_RDPMC);
 	svm_set_intercept(svm, INTERCEPT_CPUID);
@@ -1923,7 +1931,7 @@ static int npf_interception(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	u64 fault_address = __sme_clr(svm->vmcb->control.exit_info_2);
+	u64 fault_address = svm->vmcb->control.exit_info_2;
 	u64 error_code = svm->vmcb->control.exit_info_1;
 
 	trace_kvm_page_fault(fault_address, error_code);
@@ -2106,6 +2114,11 @@ static int nmi_interception(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static int smi_interception(struct kvm_vcpu *vcpu)
+{
+	return 1;
+}
+
 static int intr_interception(struct kvm_vcpu *vcpu)
 {
 	++vcpu->stat.irq_exits;
@@ -2941,7 +2954,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 			svm_disable_lbrv(vcpu);
 		break;
 	case MSR_VM_HSAVE_PA:
-		svm->nested.hsave_msr = data;
+		/*
+		 * Old kernels did not validate the value written to
+		 * MSR_VM_HSAVE_PA.  Allow KVM_SET_MSR to set an invalid
+		 * value to allow live migrating buggy or malicious guests
+		 * originating from those kernels.
+		 */
+		if (!msr->host_initiated && !page_address_valid(vcpu, data))
+			return 1;
+
+		svm->nested.hsave_msr = data & PAGE_MASK;
 		break;
 	case MSR_VM_CR:
 		return svm_set_vm_cr(vcpu, data);
@@ -3080,8 +3102,7 @@ static int (*const svm_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[SVM_EXIT_EXCP_BASE + GP_VECTOR]	= gp_interception,
 	[SVM_EXIT_INTR]				= intr_interception,
 	[SVM_EXIT_NMI]				= nmi_interception,
-	[SVM_EXIT_SMI]				= kvm_emulate_as_nop,
-	[SVM_EXIT_INIT]				= kvm_emulate_as_nop,
+	[SVM_EXIT_SMI]				= smi_interception,
 	[SVM_EXIT_VINTR]			= interrupt_window_interception,
 	[SVM_EXIT_RDPMC]			= kvm_emulate_rdpmc,
 	[SVM_EXIT_CPUID]			= kvm_emulate_cpuid,
@@ -4288,6 +4309,7 @@ static int svm_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
 static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
+	struct kvm_host_map map_save;
 	int ret;
 
 	if (is_guest_mode(vcpu)) {
@@ -4303,6 +4325,29 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
 		ret = nested_svm_vmexit(svm);
 		if (ret)
 			return ret;
+
+		/*
+		 * KVM uses VMCB01 to store L1 host state while L2 runs but
+		 * VMCB01 is going to be used during SMM and thus the state will
+		 * be lost. Temporary save non-VMLOAD/VMSAVE state to the host save
+		 * area pointed to by MSR_VM_HSAVE_PA. APM guarantees that the
+		 * format of the area is identical to guest save area offsetted
+		 * by 0x400 (matches the offset of 'struct vmcb_save_area'
+		 * within 'struct vmcb'). Note: HSAVE area may also be used by
+		 * L1 hypervisor to save additional host context (e.g. KVM does
+		 * that, see svm_prepare_guest_switch()) which must be
+		 * preserved.
+		 */
+		if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr),
+				 &map_save) == -EINVAL)
+			return 1;
+
+		BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400);
+
+		svm_copy_vmrun_state(&svm->vmcb01.ptr->save,
+				     map_save.hva + 0x400);
+
+		kvm_vcpu_unmap(vcpu, &map_save, true);
 	}
 	return 0;
 }
@@ -4310,13 +4355,14 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
 static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
-	struct kvm_host_map map;
+	struct kvm_host_map map, map_save;
 	int ret = 0;
 
 	if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) {
 		u64 saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0);
 		u64 guest = GET_SMSTATE(u64, smstate, 0x7ed8);
 		u64 vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0);
+		struct vmcb *vmcb12;
 
 		if (guest) {
 			if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM))
@@ -4332,8 +4378,25 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
 			if (svm_allocate_nested(svm))
 				return 1;
 
-			ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, map.hva);
+			vmcb12 = map.hva;
+
+			nested_load_control_from_vmcb12(svm, &vmcb12->control);
+
+			ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12);
 			kvm_vcpu_unmap(vcpu, &map, true);
+
+			/*
+			 * Restore L1 host state from L1 HSAVE area as VMCB01 was
+			 * used during SMM (see svm_enter_smm())
+			 */
+			if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr),
+					 &map_save) == -EINVAL)
+				return 1;
+
+			svm_copy_vmrun_state(map_save.hva + 0x400,
+					     &svm->vmcb01.ptr->save);
+
+			kvm_vcpu_unmap(vcpu, &map_save, true);
 		}
 	}
 
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index f89b623bb591e8..7e2090752d8fce 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -31,6 +31,7 @@
 #define MSRPM_OFFSETS	16
 extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
 extern bool npt_enabled;
+extern bool intercept_smi;
 
 /*
  * Clean bits in VMCB.
@@ -463,6 +464,8 @@ void svm_leave_nested(struct vcpu_svm *svm);
 void svm_free_nested(struct vcpu_svm *svm);
 int svm_allocate_nested(struct vcpu_svm *svm);
 int nested_svm_vmrun(struct kvm_vcpu *vcpu);
+void svm_copy_vmrun_state(struct vmcb_save_area *from_save,
+			  struct vmcb_save_area *to_save);
 void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb);
 int nested_svm_vmexit(struct vcpu_svm *svm);
 
@@ -479,6 +482,8 @@ int nested_svm_check_permissions(struct kvm_vcpu *vcpu);
 int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
 			       bool has_error_code, u32 error_code);
 int nested_svm_exit_special(struct vcpu_svm *svm);
+void nested_load_control_from_vmcb12(struct vcpu_svm *svm,
+				     struct vmcb_control_area *control);
 void nested_sync_control_from_vmcb02(struct vcpu_svm *svm);
 void nested_vmcb02_compute_g_pat(struct vcpu_svm *svm);
 void svm_switch_vmcb(struct vcpu_svm *svm, struct kvm_vmcb_info *target_vmcb);
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 3979a947933afb..db88ed4f2121c1 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -14,8 +14,6 @@
 #include "vmx_ops.h"
 #include "cpuid.h"
 
-extern const u32 vmx_msr_index[];
-
 #define MSR_TYPE_R	1
 #define MSR_TYPE_W	2
 #define MSR_TYPE_RW	3
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c6dc1b44523156..a4fd10604f7228 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -9601,6 +9601,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		set_debugreg(vcpu->arch.eff_db[3], 3);
 		set_debugreg(vcpu->arch.dr6, 6);
 		vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD;
+	} else if (unlikely(hw_breakpoint_active())) {
+		set_debugreg(0, 7);
 	}
 
 	for (;;) {
@@ -10985,9 +10987,6 @@ int kvm_arch_hardware_setup(void *opaque)
 	int r;
 
 	rdmsrl_safe(MSR_EFER, &host_efer);
-	if (WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_NX) &&
-			 !(host_efer & EFER_NX)))
-		return -EIO;
 
 	if (boot_cpu_has(X86_FEATURE_XSAVES))
 		rdmsrl(MSR_IA32_XSS, host_xss);
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 615ab254899d3b..010b59b1391764 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -45,6 +45,7 @@ enum vm_guest_mode {
 	VM_MODE_P40V48_64K,
 	VM_MODE_PXXV48_4K,	/* For 48bits VA but ANY bits PA */
 	VM_MODE_P47V64_4K,
+	VM_MODE_P44V64_4K,
 	NUM_VM_MODES,
 };
 
@@ -62,7 +63,7 @@ enum vm_guest_mode {
 
 #elif defined(__s390x__)
 
-#define VM_MODE_DEFAULT			VM_MODE_P47V64_4K
+#define VM_MODE_DEFAULT			VM_MODE_P44V64_4K
 #define MIN_PAGE_SHIFT			12U
 #define ptes_per_page(page_size)	((page_size) / 16)
 
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index 9f49f6caafe5d6..632b74d6b3cac3 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -401,7 +401,7 @@ unexpected_exception:
 void vm_init_descriptor_tables(struct kvm_vm *vm)
 {
 	vm->handlers = vm_vaddr_alloc(vm, sizeof(struct handlers),
-			vm->page_size, 0, 0);
+			vm->page_size);
 
 	*(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers;
 }
diff --git a/tools/testing/selftests/kvm/lib/guest_modes.c b/tools/testing/selftests/kvm/lib/guest_modes.c
index 25bff307c71f2a..c330f414ef96dc 100644
--- a/tools/testing/selftests/kvm/lib/guest_modes.c
+++ b/tools/testing/selftests/kvm/lib/guest_modes.c
@@ -22,6 +22,22 @@ void guest_modes_append_default(void)
 		}
 	}
 #endif
+#ifdef __s390x__
+	{
+		int kvm_fd, vm_fd;
+		struct kvm_s390_vm_cpu_processor info;
+
+		kvm_fd = open_kvm_dev_path_or_exit();
+		vm_fd = ioctl(kvm_fd, KVM_CREATE_VM, 0);
+		kvm_device_access(vm_fd, KVM_S390_VM_CPU_MODEL,
+				  KVM_S390_VM_CPU_PROCESSOR, &info, false);
+		close(vm_fd);
+		close(kvm_fd);
+		/* Starting with z13 we have 47bits of physical address */
+		if (info.ibc >= 0x30)
+			guest_mode_append(VM_MODE_P47V64_4K, true, true);
+	}
+#endif
 }
 
 void for_each_guest_mode(void (*func)(enum vm_guest_mode, void *), void *arg)
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 5b56b57b3c2078..10a8ed691c6693 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -176,6 +176,7 @@ const char *vm_guest_mode_string(uint32_t i)
 		[VM_MODE_P40V48_64K]	= "PA-bits:40,  VA-bits:48, 64K pages",
 		[VM_MODE_PXXV48_4K]	= "PA-bits:ANY, VA-bits:48,  4K pages",
 		[VM_MODE_P47V64_4K]	= "PA-bits:47,  VA-bits:64,  4K pages",
+		[VM_MODE_P44V64_4K]	= "PA-bits:44,  VA-bits:64,  4K pages",
 	};
 	_Static_assert(sizeof(strings)/sizeof(char *) == NUM_VM_MODES,
 		       "Missing new mode strings?");
@@ -194,6 +195,7 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = {
 	{ 40, 48, 0x10000, 16 },
 	{  0,  0,  0x1000, 12 },
 	{ 47, 64,  0x1000, 12 },
+	{ 44, 64,  0x1000, 12 },
 };
 _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES,
 	       "Missing new mode params?");
@@ -282,6 +284,9 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 	case VM_MODE_P47V64_4K:
 		vm->pgtable_levels = 5;
 		break;
+	case VM_MODE_P44V64_4K:
+		vm->pgtable_levels = 5;
+		break;
 	default:
 		TEST_FAIL("Unknown guest mode, mode: 0x%x", mode);
 	}
diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c
index 85b18bb8f7624a..72a1c9b4882cb8 100644
--- a/tools/testing/selftests/kvm/set_memory_region_test.c
+++ b/tools/testing/selftests/kvm/set_memory_region_test.c
@@ -377,7 +377,8 @@ static void test_add_max_memory_regions(void)
 		(max_mem_slots - 1), MEM_REGION_SIZE >> 10);
 
 	mem = mmap(NULL, (size_t)max_mem_slots * MEM_REGION_SIZE + alignment,
-		   PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+		   PROT_READ | PROT_WRITE,
+		   MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE, -1, 0);
 	TEST_ASSERT(mem != MAP_FAILED, "Failed to mmap() host");
 	mem_aligned = (void *)(((size_t) mem + alignment - 1) & ~(alignment - 1));
 
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c
index 42bd658f52a827..af27c7e829c195 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c
@@ -615,7 +615,7 @@ int main(void)
 
 	vm_init_descriptor_tables(vm);
 	vcpu_init_descriptor_tables(vm, VCPU_ID);
-	vm_handle_exception(vm, GP_VECTOR, guest_gp_handler);
+	vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler);
 
 	pr_info("Testing access to Hyper-V specific MSRs\n");
 	guest_test_msrs_access(vm, addr_gva2hva(vm, msr_gva),
diff --git a/tools/testing/selftests/kvm/x86_64/mmu_role_test.c b/tools/testing/selftests/kvm/x86_64/mmu_role_test.c
index 523371cf8e8f7b..da2325fcad87bf 100644
--- a/tools/testing/selftests/kvm/x86_64/mmu_role_test.c
+++ b/tools/testing/selftests/kvm/x86_64/mmu_role_test.c
@@ -71,7 +71,7 @@ static void mmu_role_test(u32 *cpuid_reg, u32 evil_cpuid_val)
 	/* Set up a #PF handler to eat the RSVD #PF and signal all done! */
 	vm_init_descriptor_tables(vm);
 	vcpu_init_descriptor_tables(vm, VCPU_ID);
-	vm_handle_exception(vm, PF_VECTOR, guest_pf_handler);
+	vm_install_exception_handler(vm, PF_VECTOR, guest_pf_handler);
 
 	r = _vcpu_run(vm, VCPU_ID);
 	TEST_ASSERT(r == 0, "vcpu_run failed: %d\n", r);
diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c
index c1f831803ad2df..d0fe2fdce58c47 100644
--- a/tools/testing/selftests/kvm/x86_64/smm_test.c
+++ b/tools/testing/selftests/kvm/x86_64/smm_test.c
@@ -53,15 +53,28 @@ static inline void sync_with_host(uint64_t phase)
 		     : "+a" (phase));
 }
 
-void self_smi(void)
+static void self_smi(void)
 {
 	x2apic_write_reg(APIC_ICR,
 			 APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_SMI);
 }
 
-void guest_code(void *arg)
+static void l2_guest_code(void)
 {
+	sync_with_host(8);
+
+	sync_with_host(10);
+
+	vmcall();
+}
+
+static void guest_code(void *arg)
+{
+	#define L2_GUEST_STACK_SIZE 64
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
 	uint64_t apicbase = rdmsr(MSR_IA32_APICBASE);
+	struct svm_test_data *svm = arg;
+	struct vmx_pages *vmx_pages = arg;
 
 	sync_with_host(1);
 
@@ -74,21 +87,50 @@ void guest_code(void *arg)
 	sync_with_host(4);
 
 	if (arg) {
-		if (cpu_has_svm())
-			generic_svm_setup(arg, NULL, NULL);
-		else
-			GUEST_ASSERT(prepare_for_vmx_operation(arg));
+		if (cpu_has_svm()) {
+			generic_svm_setup(svm, l2_guest_code,
+					  &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+		} else {
+			GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+			GUEST_ASSERT(load_vmcs(vmx_pages));
+			prepare_vmcs(vmx_pages, l2_guest_code,
+				     &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+		}
 
 		sync_with_host(5);
 
 		self_smi();
 
 		sync_with_host(7);
+
+		if (cpu_has_svm()) {
+			run_guest(svm->vmcb, svm->vmcb_gpa);
+			svm->vmcb->save.rip += 3;
+			run_guest(svm->vmcb, svm->vmcb_gpa);
+		} else {
+			vmlaunch();
+			vmresume();
+		}
+
+		/* Stages 8-11 are eaten by SMM (SMRAM_STAGE reported instead) */
+		sync_with_host(12);
 	}
 
 	sync_with_host(DONE);
 }
 
+void inject_smi(struct kvm_vm *vm)
+{
+	struct kvm_vcpu_events events;
+
+	vcpu_events_get(vm, VCPU_ID, &events);
+
+	events.smi.pending = 1;
+	events.flags |= KVM_VCPUEVENT_VALID_SMM;
+
+	vcpu_events_set(vm, VCPU_ID, &events);
+}
+
 int main(int argc, char *argv[])
 {
 	vm_vaddr_t nested_gva = 0;
@@ -147,6 +189,22 @@ int main(int argc, char *argv[])
 			    "Unexpected stage: #%x, got %x",
 			    stage, stage_reported);
 
+		/*
+		 * Enter SMM during L2 execution and check that we correctly
+		 * return from it. Do not perform save/restore while in SMM yet.
+		 */
+		if (stage == 8) {
+			inject_smi(vm);
+			continue;
+		}
+
+		/*
+		 * Perform save/restore while the guest is in SMM triggered
+		 * during L2 execution.
+		 */
+		if (stage == 10)
+			inject_smi(vm);
+
 		state = vcpu_save_state(vm, VCPU_ID);
 		kvm_vm_release(vm);
 		kvm_vm_restart(vm, O_RDWR);
diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c
index f08f5e82460b1d..0be80c213f7f25 100644
--- a/virt/kvm/coalesced_mmio.c
+++ b/virt/kvm/coalesced_mmio.c
@@ -186,7 +186,6 @@ int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm,
 		    coalesced_mmio_in_range(dev, zone->addr, zone->size)) {
 			r = kvm_io_bus_unregister_dev(kvm,
 				zone->pio ? KVM_PIO_BUS : KVM_MMIO_BUS, &dev->dev);
-			kvm_iodevice_destructor(&dev->dev);
 
 			/*
 			 * On failure, unregister destroys all devices on the
@@ -196,6 +195,7 @@ int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm,
 			 */
 			if (r)
 				break;
+			kvm_iodevice_destructor(&dev->dev);
 		}
 	}
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 7d95126cda9e12..986959833d701e 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -935,7 +935,7 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
 		stat_data->kvm = kvm;
 		stat_data->desc = pdesc;
 		stat_data->kind = KVM_STAT_VCPU;
-		kvm->debugfs_stat_data[i] = stat_data;
+		kvm->debugfs_stat_data[i + kvm_vm_stats_header.num_desc] = stat_data;
 		debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc),
 				    kvm->debugfs_dentry, stat_data,
 				    &stat_fops_per_vm);